{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TSHT7325SQDZSHP5J5VKESR6MJ","short_pith_number":"pith:TSHT7325","canonical_record":{"source":{"id":"2504.15252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:33:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"ef90171b712267c073b49dc97ff0a7044b37f93d201cc56152e3842631756c03","abstract_canon_sha256":"156ba1419806a30cd1d5b630fea93ed2062d4b135b2b25b48f5eb6956c449e9b"},"schema_version":"1.0"},"canonical_sha256":"9c8f3fef5d9407991dfd4f6aa24a3e626b22112bbeccd57c2be6662ae0ce6d61","source":{"kind":"arxiv","id":"2504.15252","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15252","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15252v1","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15252","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_12","alias_value":"TSHT7325SQDZ","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_16","alias_value":"TSHT7325SQDZSHP5","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_8","alias_value":"TSHT7325","created_at":"2026-07-05T10:55:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TSHT7325SQDZSHP5J5VKESR6MJ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:33:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"ef90171b712267c073b49dc97ff0a7044b37f93d201cc56152e3842631756c03","abstract_canon_sha256":"156ba1419806a30cd1d5b630fea93ed2062d4b135b2b25b48f5eb6956c449e9b"},"schema_version":"1.0"},"canonical_sha256":"9c8f3fef5d9407991dfd4f6aa24a3e626b22112bbeccd57c2be6662ae0ce6d61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:55.028816Z","signature_b64":"bQzKJjdIaAwLNpeHI2hjMnmRr7QxORyhtZg4Whq9xeBhzI0gfUUU6RTL+bt4QgTGQ71IG/n8aFYOpAQCUJr7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8f3fef5d9407991dfd4f6aa24a3e626b22112bbeccd57c2be6662ae0ce6d61","last_reissued_at":"2026-07-05T10:55:55.028321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:55.028321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15252","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htati7k4ip7btovEsb8wfi8ozYnLqBJdI8DNWhV6Atx+shsmD8p2S6BD514lRQezch9dEW6I9wkNBcLTswlYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:29:39.883159Z"},"content_sha256":"14b3db003fc63ae866be7e881f46bf41ba0c460dab98614a18299af7ef1d4bad","schema_version":"1.0","event_id":"sha256:14b3db003fc63ae866be7e881f46bf41ba0c460dab98614a18299af7ef1d4bad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TSHT7325SQDZSHP5J5VKESR6MJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SuoiAI: Building a Dataset for Aquatic Invertebrates in Vietnam","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Duong Vu, Khuong Dinh, Lakshay Sharma, Minh Do, Trang Nguyen, Trung Phan, Tuan Dinh, Tue Vo","submitted_at":"2025-04-21T17:33:02Z","abstract_excerpt":"Understanding and monitoring aquatic biodiversity is critical for ecological health and conservation efforts. This paper proposes SuoiAI, an end-to-end pipeline for building a dataset of aquatic invertebrates in Vietnam and employing machine learning (ML) techniques for species classification. We outline the methods for data collection, annotation, and model training, focusing on reducing annotation effort through semi-supervised learning and leveraging state-of-the-art object detection and classification models. Our approach aims to overcome challenges such as data scarcity, fine-grained clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15252","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.15252/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6W/zu2Bpih7xL52RrhDFkq0hu4AD/f4iEa2Z0nLI6WzrlZ/HyAneHM+kOAFCxNUMpgxCp61fl8N7h8lBq6yDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:29:39.883662Z"},"content_sha256":"afdb847603033191608ef8ddd656f5bf7f263f28f906639f3fef39d319a6311a","schema_version":"1.0","event_id":"sha256:afdb847603033191608ef8ddd656f5bf7f263f28f906639f3fef39d319a6311a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSHT7325SQDZSHP5J5VKESR6MJ/bundle.json","state_url":"https://pith.science/pith/TSHT7325SQDZSHP5J5VKESR6MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSHT7325SQDZSHP5J5VKESR6MJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T19:29:39Z","links":{"resolver":"https://pith.science/pith/TSHT7325SQDZSHP5J5VKESR6MJ","bundle":"https://pith.science/pith/TSHT7325SQDZSHP5J5VKESR6MJ/bundle.json","state":"https://pith.science/pith/TSHT7325SQDZSHP5J5VKESR6MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSHT7325SQDZSHP5J5VKESR6MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TSHT7325SQDZSHP5J5VKESR6MJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"156ba1419806a30cd1d5b630fea93ed2062d4b135b2b25b48f5eb6956c449e9b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:33:02Z","title_canon_sha256":"ef90171b712267c073b49dc97ff0a7044b37f93d201cc56152e3842631756c03"},"schema_version":"1.0","source":{"id":"2504.15252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15252","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15252v1","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15252","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_12","alias_value":"TSHT7325SQDZ","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_16","alias_value":"TSHT7325SQDZSHP5","created_at":"2026-07-05T10:55:55Z"},{"alias_kind":"pith_short_8","alias_value":"TSHT7325","created_at":"2026-07-05T10:55:55Z"}],"graph_snapshots":[{"event_id":"sha256:afdb847603033191608ef8ddd656f5bf7f263f28f906639f3fef39d319a6311a","target":"graph","created_at":"2026-07-05T10:55:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.15252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding and monitoring aquatic biodiversity is critical for ecological health and conservation efforts. This paper proposes SuoiAI, an end-to-end pipeline for building a dataset of aquatic invertebrates in Vietnam and employing machine learning (ML) techniques for species classification. We outline the methods for data collection, annotation, and model training, focusing on reducing annotation effort through semi-supervised learning and leveraging state-of-the-art object detection and classification models. Our approach aims to overcome challenges such as data scarcity, fine-grained clas","authors_text":"Duong Vu, Khuong Dinh, Lakshay Sharma, Minh Do, Trang Nguyen, Trung Phan, Tuan Dinh, Tue Vo","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:33:02Z","title":"SuoiAI: Building a Dataset for Aquatic Invertebrates in Vietnam"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15252","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:14b3db003fc63ae866be7e881f46bf41ba0c460dab98614a18299af7ef1d4bad","target":"record","created_at":"2026-07-05T10:55:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"156ba1419806a30cd1d5b630fea93ed2062d4b135b2b25b48f5eb6956c449e9b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T17:33:02Z","title_canon_sha256":"ef90171b712267c073b49dc97ff0a7044b37f93d201cc56152e3842631756c03"},"schema_version":"1.0","source":{"id":"2504.15252","kind":"arxiv","version":1}},"canonical_sha256":"9c8f3fef5d9407991dfd4f6aa24a3e626b22112bbeccd57c2be6662ae0ce6d61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c8f3fef5d9407991dfd4f6aa24a3e626b22112bbeccd57c2be6662ae0ce6d61","first_computed_at":"2026-07-05T10:55:55.028321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:55.028321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQzKJjdIaAwLNpeHI2hjMnmRr7QxORyhtZg4Whq9xeBhzI0gfUUU6RTL+bt4QgTGQ71IG/n8aFYOpAQCUJr7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:55.028816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14b3db003fc63ae866be7e881f46bf41ba0c460dab98614a18299af7ef1d4bad","sha256:afdb847603033191608ef8ddd656f5bf7f263f28f906639f3fef39d319a6311a"],"state_sha256":"d252cd06f3301447e8160e024f9ad330d239e2bc765ce038f8c1135ff833d1dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a87oAkJdq+VI4qVD0dUCq8ZFG6fl91olHd2Tpr3YwY4dsWo0g5qD9t+X/oVda0KqnAK+cfxbxZ4Po7SFjLfzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:29:39.887730Z","bundle_sha256":"6c9ddc1d55ac4fca5bd54d29f67f77c810a37cf22004ccd316fa8a538a11cbb2"}}